There isn't one. For the above example, you will notice an entry for a non mapreduce job in the namenode log similar to this example;
hadoop-hdfs-namenode.log:2018-08-24 06:44:41,819 INFO hdfs.StateChange (FSNamesystem.java:completeFile(3759)) - DIR* completeFile: /user/hadoop/file1.dat._COPYING_ is closed by DFSClient_NONMAPREDUCE_956954044_1
What happens is; the client used the create() operation defined in the DistributedFileSystem class, and then makes use of the DFSOutputStream class to write to the an internal queue, called the 'data queue' which is used by the datastreamer, which in turn will allocate blocks for the data that we want to write with the copyfromlocal command. There is no mapreduce/yarn job here, which you can notice from the NONMAPREDUCE entry in the namenode log. For some other tools, such as distcp, you would see mapreduce involved.